Summarize the problem: Received an error
1 # predict the test dataset
----> 2 yhat = model.predict(X_test)
File c:\Users\nwm2\Anaconda3\lib\site-packages\sklearn\linear_model\_base.py:425, in LinearClassifierMixin.predict(self, X)
411 def predict(self, X):
412 """
413 Predict class labels for samples in X.
414
(...)
423 Vector containing the class labels for each sample.
424 """
--> 425 scores = self.decision_function(X)
426 if len(scores.shape) == 1:
427 indices = (scores > 0).astype(int)
File c:\Users\nwm2\Anaconda3\lib\site-packages\sklearn\linear_model\_base.py:407, in LinearClassifierMixin.decision_function(self, X)
387 """
388 Predict confidence scores for samples.
389
(...)
403 this class would be predicted.
404 """
...
118 )
119 # for object dtype data, we only check for NaNs (GH-13254)
120 elif X.dtype == np.dtype("object") and not allow_nan:
"ValueError: Input contains NaN, infinity or a value too large for dtype('float64')."
Provide details and any research: Converting breast cancer dataset - categorical data into numbers using feature-engine. Seems to work up to - yhat = model.predict(X_test) with above error.
I've tried checking for nans in my dataset but there's none.
Here's the code
# load libraries
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from feature_engine.encoding import OrdinalEncoder
import pandas as pd
from sklearn.metrics import mean_absolute_error
from sklearn.metrics import r2_score
# load dataset
df = pd.read_csv('https://raw.githubusercontent.com/jbrownlee/Datasets/master/breast-cancer.csv', header=None)
df.head()
# assign labels to features
names = ['Age', 'Menopause', 'Tumor-Size', 'Inv-Nodes', 'Node-Caps', 'Deg-Malig', 'Breast', 'Breast-Quad', 'Irradiat', 'Class']
df.columns = names
# use a loop to determine which features are categorical and which are numerical
for name in names:
if name != 'Class':
if df[name].dtype == 'object':
print(name, 'is categorical')
else:
print(name, 'is numerical')
# print out the number of categorical features
print('Number of categorical features:', len(df.select_dtypes(include=['object'])))
# print out the number of numerical features
print('Number of numerical features:', len(df.select_dtypes(include=['number'])))
# use train test split method from scikit-learn library to seperate dataset into 70% training and 30% test
X_train, X_test, y_train, y_test = train_test_split(df.drop(['Class'], axis=1), df['Class'], test_size=0.3, random_state=1)
# use feature_engine method Ordinal Encoder to convert categorical features to ordinal
encoder = OrdinalEncoder(encoding_method='arbitrary')
#fit the data to the model
encoder.fit(X_train)
# use transform to encode the categories to numbers
X_train = encoder.transform(X_train)
X_test = encoder.transform(X_test)
#check for nans in X_test
print(X_test.isnull().sum())
# Ordinal encode target variable y
label_encoder = LabelEncoder()
label_encoder.fit(y_train)
y_train = label_encoder.transform(y_train)
y_test = label_encoder.transform(y_test)
# check for any nans
print(df.isnull().sum())
# use logistic regression method from scikit-learn library to predict malignancy
model = LogisticRegression()
# fit the model to the training dataset
model.fit(X_train, y_train)
print(X_test.isnull().sum())
X_test = X_test.fillna(X_test.mean())
X_test.isnull().sum()
# predict the test dataset - error happens here!
yhat = model.predict(X_test)**
# print out accuracy score using accuracy_score method from scikit-learn library
accuracy_score = accuracy_score(y_test, yhat)
print('Accuracy: %.2f' % (accuracy_score * 100))
```
